工业LLM维护团队必读，教你如何在有限资源下提升模型性能，数据工程比一次性配方更重要。
本文提出工业后训练是棕地维护模式，团队需在固定计算和混合预算下改进已部署模型。研究揭示了三大挑战：零和混合设计、产量作为关键指标以及不确定性下的端到端集成。案例显示，提高教师蒸馏转化率使接受监督增加2.84倍，CodeForces pass@1提升2.59点，LiveCodeBench v6 pass@1提升6.11点。
LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly dataware: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer's perspective on why this work is hard in practice, distilling three recurring challenges, zero-sum mixture design, yield as the binding metric, and end-to-end integration under uncertainty, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by 2.84 times while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by +2.59 points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by +6.11 (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance.